"speculative decoding" Jobs

10 open tech roles matching “speculative decoding”, taken straight from company career pages — not reposted from other job boards. Most in demand right now: Python, PyTorch, CUDA. Every listing is re-checked daily and closed roles are removed.

Showing 10 of 10 results

Research Engineer, Frontier Speculative Decoding

Together AI San Francisco, New York City $190k–$270k/yr Published 8 months ago

DeepSpeed AI/ML Slurm PyTorch Python

Apply →

Research Intern, Inference (Fall 2026)

Join Together AI as a Research Intern to work on cutting-edge distributed inference and optimization for large foundation models.

Together AI San Francisco $58–$63/yr Published 1 month ago

JAX CUDA Machine Learning PyTorch Python

Flexible on stack

Apply →

Application Software Engineer, Inference Visa

Join SpaceX as an Application Software Engineer to develop high-performance AI inference systems in a mission-driven environment.

SpaceX Palo Alto, CA $135k–$185k/yr Published 1 month ago

C++ TensorRT-LLM gRPC Triton SGLang

Flexible on stack

Apply →

Member of Technical Staff (AI Inference Engineer)

Perplexity London Published 3 months ago

NVLink CuTe DSL Triton JAX CUTLASS

Apply →

AI Research Engineer - Datadog AI Research (DAIR) Remote

Datadog Paris, France Published 11 months ago

C++ Ray JAX CUDA DeepSpeed

Apply →

Member of Technical Staff (AI Inference Engineer)

Perplexity San Francisco Published 3 months ago

NVLink CuTe DSL Nsight Systems Triton JAX

Apply →

LLM Inference Frameworks and Optimization Engineer

Together AI San Francisco, Singapore, Amsterdam $160k–$230k/yr Published 1 year ago

C++ TensorRT-LLM SGLang CUDA vLLM

Apply →

AI Researcher, Core ML (Turbo)

Together AI San Francisco $200k–$280k/yr Published 2 years ago

RLAIF speculative decoding SGLang vLLM reward modeling

Apply →

Research Engineer, Core ML

Together AI San Francisco $200k–$280k/yr Published 5 months ago

LLMs RLAIF SGLang vLLM quantization

Apply →

Machine Learning Engineer - Inference

Together AI San Francisco $160k–$230k/yr Published 2 years ago

Cython TensorRT-LLM Triton CUDA vLLM

Apply →